Screening of normal endoscopic large bowel biopsies with interpretable graph learning: a retrospective study.
Screening of normal endoscopic large bowel biopsies with interpretable graph learning: a retrospective study.
复制标题
DOI：
10.1136/gutjnl-2023-329512
复制
发表时间：
2023-09
期刊：
影响因子：
24.5
通讯作者：
Rajpoot, Nasir
中科院分区：
文献类型：
--
作者：
Graham, Simon;Minhas, Fayyaz;Bilal, Mohsin;Ali, Mahmoud;Tsang, Yee Wah;Eastwood, Mark;Wahab, Noorul;Jahanifar, Mostafa;Hero, Emily;Dodd, Katherine;Sahota, Harvir;Wu, Shaobin;Lu, Wenqi;Azam, Ayesha;Benes, Ksenija;Nimir, Mohammed;Hewitt, Katherine;Bhalerao, Abhir;Robinson, Andrew;Eldaly, Hesham;Raza, Shan E. Ahmed;Gopalakrishnan, Kishore;Snead, David;Rajpoot, Nasir
开发一种可解释的人工智能算法，以排除正常的大肠内窥镜活检，节省病理学家资源，帮助早期诊断。结合病理学家领域知识开发了一个图神经网络，利用临床驱动的可解释特征，将来自3291名患者（约54%女性，46%男性）的内镜下大肠活检的6591张全片图像（WSIs）分类为正常或异常（非肿瘤和肿瘤）。一个英国国家卫生服务（NHS）网站被用于模型训练和内部验证。外部验证是对另外两个NHS站点和一个葡萄牙站点的数据进行的。对2080例患者的5054例WSIs进行模型训练和内部验证，曲线下面积-受试者工作特征（AUC-ROC）为0.98 (SD=0.004)， auc -精确-召回率（PR）为0.98 （SD=0.003）。该模型名为可解释的Gland-Graphs using a Neural Aggregator (IGUANA)，其性能在来自三个独立外部数据集的1211例患者的1537例wsi中是一致的，平均AUC-ROC=0.97 (SD=0.007), AUC-PR=0.97 （SD=0.005）。在99%的高灵敏度阈值下，所提出的模型可以将病理学家检查的正常玻片数量减少约55%。IGUANA还提供了一个可解释的输出，以热图的形式突出WSI中潜在的异常，以及将模型预测与各种组织学特征相关联的数值。该模型实现了一贯的高精度，显示了其在优化日益稀缺的病理学家资源方面的潜力。可解释的预测可以指导病理学家做出诊断决策，并有助于增强他们对算法的信心，为未来的临床应用铺平道路。
To develop an interpretable artificial intelligence algorithm to rule out normal large bowel endoscopic biopsies, saving pathologist resources and helping with early diagnosis. A graph neural network was developed incorporating pathologist domain knowledge to classify 6591 whole-slides images (WSIs) of endoscopic large bowel biopsies from 3291 patients (approximately 54% female, 46% male) as normal or abnormal (non-neoplastic and neoplastic) using clinically driven interpretable features. One UK National Health Service (NHS) site was used for model training and internal validation. External validation was conducted on data from two other NHS sites and one Portuguese site. Model training and internal validation were performed on 5054 WSIs of 2080 patients resulting in an area under the curve-receiver operating characteristic (AUC-ROC) of 0.98 (SD=0.004) and AUC-precision-recall (PR) of 0.98 (SD=0.003). The performance of the model, named Interpretable Gland-Graphs using a Neural Aggregator (IGUANA), was consistent in testing over 1537 WSIs of 1211 patients from three independent external datasets with mean AUC-ROC=0.97 (SD=0.007) and AUC-PR=0.97 (SD=0.005). At a high sensitivity threshold of 99%, the proposed model can reduce the number of normal slides to be reviewed by a pathologist by approximately 55%. IGUANA also provides an explainable output highlighting potential abnormalities in a WSI in the form of a heatmap as well as numerical values associating the model prediction with various histological features. The model achieved consistently high accuracy showing its potential in optimising increasingly scarce pathologist resources. Explainable predictions can guide pathologists in their diagnostic decision-making and help boost their confidence in the algorithm, paving the way for its future clinical adoption.
登录
查看更多内容
DOI：
10.1016/j.compmedimag.2021.102027
发表时间：
2022-01-01
影响因子：
5.7
作者：
Ahmedt-Aristizabal, David;Armin, Mohammad Ali;Petersson, Lars
通讯作者：
Petersson, Lars
影响因子：
28.1
作者：
Lu MY;Williamson DFK;Chen TY;Chen RJ;Barbieri M;Mahmood F
通讯作者：
Mahmood F
影响因子：
4.6
作者：
Bychkov D;Linder N;Turkki R;Nordling S;Kovanen PE;Verrill C;Walliander M;Lundin M;Haglund C;Lundin J
通讯作者：
Lundin J
影响因子：
10.9
作者：
Lu, Wenqi;Toss, Michael;Minhas, Fayyaz
通讯作者：
Minhas, Fayyaz
影响因子：
--
作者：
Korbar B;Olofson AM;Miraflor AP;Nicka CM;Suriawinata MA;Torresani L;Suriawinata AA;Hassanpour S
通讯作者：
Hassanpour S